Skip to content
View SpeechEE's full-sized avatar

Block or report SpeechEE

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
SpeechEE/README.md

SpeechEE

SpeechEE: A Novel Benchmark for Speech Event Extraction

Requirements

General

  • Python (verified on 3.9)
  • CUDA (verified on 11.8)

Python Packages

  • refer to requirements.txt
conda create -n envs python=3.9
conda activate envs
pip install -r requirements.txt

Data structure:

datasets
|
├── sentence-level
│   ├── PHEE
│   │   ├── train
│   │   │   ├── train-0.wav
│   │   │   ├── ...
│   │   ├── dev
│   │   │   ├── dev-0.wav
│   │   │   ├── ...
│   │   ├── test
│   │   │   ├── test-0.wav
│   │   │   ├── ...
|
├── document-level ...
|
├── dialogue-level ...

Running SpeechEE

The command for training model is as follows:

bash run.bash -d 0 -f tree -m t5-large --label_smoothing 0 -l 5e-5 --lr_scheduler linear --warmup_steps 2000 -b 16 -i PHEE
  • -d refers to the GPU device id.
  • -m t5-large refers to using T5-large as the textual decoder.
  • -i refers to the dataset.

Popular repositories Loading

  1. SpeechEE SpeechEE Public

    Python 11

  2. SpeechEE.github.io SpeechEE.github.io Public

    JavaScript

  3. challenge challenge Public

    JavaScript